© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 32
    Prev
    Next
    INDEX
    Explanations

    perpendicular

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .roles
    -0.07
     assistant
    -0.07
     
    -0.07
     vill
    -0.07
     eiland
    -0.07
     काय
    -0.07
    ائح
    -0.07
     eru
    -0.07
    enh
    -0.07
     lank
    -0.07
    POSITIVE LOGITS
     poging
    0.08
    (OS
    0.08
    (FILE
    0.08
     подобрать
    0.08
     приобрести
    0.08
     Prüfung
    0.08
     Заб
    0.08
     Ғ
    0.08
     लगाने
    0.08
     MEMBERS
    0.08
    Activations Density 0.009%

    No Known Activations